© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72747
    Prev
    Next
    INDEX
    Explanations

    clauses introduced by where or which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <td>
    -1.59
    ]}{
    -1.41
     termasuk
    -1.30
     în
    -1.28
    irdre
    -1.26
    鎮
    -1.24
     prairie
    -1.24
    ellä
    -1.23
     referirse
    -1.23
    мый
    -1.23
    POSITIVE LOGITS
    余談
    1.79
     través
    1.73
    嘖
    1.70
     ждет
    1.59
     живет
    1.56
    年から
    1.46
     идет
    1.42
    through
    1.42
     if
    1.41
     идёт
    1.41
    Activations Density 0.053%

    No Known Activations